←back to thread

AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

(www.phoronix.com)
1045 points mfiguiere | 3 comments | 12 Feb 24 14:00 UTC | HN request time: 0.849s | source
Show context
AndrewKemendo ◴[12 Feb 24 14:53 UTC] No.39345391[source]▶
ROCm is not spelled out anywhere in their documentation and the best answers in search come from Github and not AMD official documents

"Radeon Open Compute Platform"

https://github.com/ROCm/ROCm/issues/1628

And they wonder why they are losing. Branding absolutely matters.

replies(8): >>39345468 #>>39345472 #>>39345491 #>>39345516 #>>39345873 #>>39345947 #>>39345989 #>>39352446 #
1. marcus0x62 ◴[12 Feb 24 15:00 UTC] No.39345472[source]▶
That, and it only runs on a handful of their GPUs.
replies(1): >>39345568 #
2. NekkoDroid ◴[12 Feb 24 15:07 UTC] No.39345568[source]▶
If you are talking about the "supported" list of GPUs, those listed are only the ones they fully validate and QA test, other of same gen are likely to work, but most likely with some bumps along the way. In one of the a bit older phoronix posts about ROCm one of their engeneers did say they are trying to expand the list of validated & QA'd cards, as well as destinguishing between "validated", "supported" and "non-functional"
replies(1): >>39351587 #
3. machomaster ◴[12 Feb 24 22:45 UTC] No.39351587[source]▶
They can say whatever but the action is what matters, not wishes and promises. And the reality is that list of supported GPUs has been unchanged since they first announced it a year ago.